Visualizing Neural Networks with the Grand Tour
By focusing on linear dimensionality reduction, we show how to visualize many dynamic phenomena in neural networks.
Full feed
Feed 5,767 posts
Every story across every category, newest first. Each card links to the original publisher; daily-brief posts open as editorial pages.
Thread: Circuits
What can we learn if we invest heavily in reverse engineering a single neural network?
Zoom In: An Introduction to Circuits
By studying the connections between neurons, we can find meaningful algorithms in the weights of neural networks.
Growing Neural Cellular Automata
Training an end-to-end differentiable, self-organising cellular automata model of morphogenesis, able to both grow and regenerate specific patterns.
Curriculum for Reinforcement Learning
[Updated on 2020-02-03: mentioning PCG in the “Task-Specific Curriculum” section. [Updated on 2020-02-04: Add a new “curriculum through distillation” section.
Visualizing the Impact of Feature Attribution Baselines
Exploring the baseline input hyperparameter, and how it impacts interpretations of neural network behavior.
Computing Receptive Fields of Convolutional Neural Networks
Detailed derivations and open-source code to analyze the receptive fields of convnets.